Imagen tomada de Forbes

Imagen tomada de Forbes

1. Introducción

La lista de multimillonarios publicada anualmente por Forbes es una de las referencias más emblemáticas para conocer la distribución de la riqueza extrema en el mundo. Cada año, este listado recopila información sobre las personas más ricas del planeta, incluyendo su patrimonio neto estimado, país de origen, fuente de riqueza y el sector económico en el que se desempeñan.

Este proyecto tiene un doble propósito:

Para ello, se utilizará el lenguaje de programación R y algunas de sus librerías más conocidas en el entorno del análisis de datos, como dplyr, ggplot2, y tidyverse, entre otras.

¿Qué analizaremos?

A lo largo del documento se responderán preguntas como:

Además, se crearán nuevas variables como una clasificación binaria que indica si un multimillonario pertenece a la Unión Europea, Estados Unidos o China, lo que permitirá realizar comparaciones más enriquecidas.

También se implementarán visualizaciones geoespaciales mediante la librería rnaturalearth que ayuden a comprender mejor la distribución global de la riqueza extrema.

2. Exploración y limpieza del DataSet

2.1 Lectura del archivo

# Cargar librerías
library(readxl)
library(dplyr)
library(stringr)
library(ggplot2)
library(tidyverse)
library(kableExtra)
library(treemapify)
library(ggrepel)
library(rnaturalearth)
library(sf)


# Leer el archivo Excel
forbes <- read_excel("FORBES.xlsx")

2.2 Dimensiones del Dataset

# Número de filas y columnas
dim(forbes)
## [1] 3077    7
# Nombres de las variables
colnames(forbes)
## [1] "Rank"      "Name"      "Net Worth" "Age"       "Country"   "Source"   
## [7] "Industry"
# Categorías y conteo por variable "Industry"
forbes %>%
  count(Industry, sort = TRUE)
## # A tibble: 18 × 2
##    Industry                       n
##    <chr>                      <int>
##  1 Finance & Investments        466
##  2 Technology                   413
##  3 Manufacturing                343
##  4 Fashion & Retail             300
##  5 Healthcare                   233
##  6 Food & Beverage              231
##  7 Diversified                  217
##  8 Real Estate                  205
##  9 Media & Entertainment        118
## 10 Energy                       105
## 11 Metals & Mining               78
## 12 Automotive                    77
## 13 Logistics                     65
## 14 Sports                        61
## 15 Service                       57
## 16 Construction & Engineering    53
## 17 Telecom                       32
## 18 Gambling & Casinos            23

2.3 Tipos de variables y estructura general

# Vista general de las variables
glimpse(forbes)
## Rows: 3,077
## Columns: 7
## $ Rank        <dbl> 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17,…
## $ Name        <chr> "Elon Musk", "Mark Zuckerberg", "Jeff Bezos", "Larry Ellis…
## $ `Net Worth` <chr> "$342 B", "$216 B", "$215 B", "$192 B", "$178 B", "$154 B"…
## $ Age         <dbl> 53, 40, 61, 80, 76, 94, 52, 51, 89, 69, 80, 76, 69, 83, 75…
## $ Country     <chr> "United States", "United States", "United States", "United…
## $ Source      <chr> "Tesla, SpaceX", "Facebook", "Amazon", "Oracle", "LVMH", "…
## $ Industry    <chr> "Automotive", "Technology", "Technology", "Technology", "F…
# El comando "str" también se puede usar para obtener información general de las variables
str(forbes)
## tibble [3,077 × 7] (S3: tbl_df/tbl/data.frame)
##  $ Rank     : num [1:3077] 1 2 3 4 5 6 7 8 9 10 ...
##  $ Name     : chr [1:3077] "Elon Musk" "Mark Zuckerberg" "Jeff Bezos" "Larry Ellison" ...
##  $ Net Worth: chr [1:3077] "$342 B" "$216 B" "$215 B" "$192 B" ...
##  $ Age      : num [1:3077] 53 40 61 80 76 94 52 51 89 69 ...
##  $ Country  : chr [1:3077] "United States" "United States" "United States" "United States" ...
##  $ Source   : chr [1:3077] "Tesla, SpaceX" "Facebook" "Amazon" "Oracle" ...
##  $ Industry : chr [1:3077] "Automotive" "Technology" "Technology" "Technology" ...

2.4 Revisión de valores faltantes, nulos y duplicados

# Verificar valores faltantes
colSums(is.na(forbes))
##      Rank      Name Net Worth       Age   Country    Source  Industry 
##         0         0         0        40         0         0         0
# Verificar duplicados
sum(duplicated(forbes))
## [1] 134
# Eliminar duplicados
forbes <- forbes %>% distinct()

# Estadísticas generales para detectar outliers
summary(forbes)
##       Rank          Name            Net Worth              Age        
##  Min.   :   1   Length:2943        Length:2943        Min.   : 19.00  
##  1st Qu.: 734   Class :character   Class :character   1st Qu.: 57.00  
##  Median :1462   Mode  :character   Mode  :character   Median : 66.00  
##  Mean   :1465                                         Mean   : 65.52  
##  3rd Qu.:2233                                         3rd Qu.: 75.00  
##  Max.   :2933                                         Max.   :103.00  
##                                                       NA's   :38      
##    Country             Source            Industry        
##  Length:2943        Length:2943        Length:2943       
##  Class :character   Class :character   Class :character  
##  Mode  :character   Mode  :character   Mode  :character  
##                                                          
##                                                          
##                                                          
##

2.5 Conversión de tipos de variables

# Convertir "Net Worth" a número
forbes <- forbes %>%
  mutate(NetWorth = as.numeric(str_remove_all(`Net Worth`, "[$B]")))

2.6 Generación de nuevas variables

Variables binarias: Pertenencia a la Unión Europea, Estados Unidos y China

Para mejoras en el análisis geopolítico:

# Lista de países de la UE+

# Lista ampliada de países europeos (2025)

european_countries <- c("Germany", "France", "Italy", "Spain", "Netherlands",
                        "Poland", "Sweden", "Belgium", "Austria", "Denmark",
                        "Finland", "Portugal", "Ireland", "Czech Republic",
                        "Greece", "Hungary", "Slovakia", "Bulgaria", "Croatia",
                        "Lithuania", "Slovenia", "Latvia", "Estonia", "Luxembourg",
                        "Malta", "Cyprus", "Romania",
                        # No UE
                        "United Kingdom", "Switzerland", "Norway", "Iceland",
                        "Serbia", "Ukraine", "Bosnia and Herzegovina", "Albania",
                        "North Macedonia", "Moldova", "Kosovo", "Monaco",
                        "Liechtenstein", "Andorra", "San Marino")
# Variables dummy por región/país
forbes <- forbes %>%
  mutate(
    Is_Europe = if_else(Country %in% european_countries, 1, 0),
    Is_EEUU = if_else(Country == "United States", 1, 0),
    Is_China = if_else(Country == "China", 1, 0)
  )

3. Análisis descriptivo general

3.1 Estadísticas generales de los multimillonarios

Estadísticas descriptivas de las variables cuantitativas NetWorth y Age:

# Estadísticas descriptivas para variables numéricas
summary(select(forbes, NetWorth, Age))
##     NetWorth            Age        
##  Min.   :  1.000   Min.   : 19.00  
##  1st Qu.:  1.500   1st Qu.: 57.00  
##  Median :  2.500   Median : 66.00  
##  Mean   :  5.404   Mean   : 65.52  
##  3rd Qu.:  4.900   3rd Qu.: 75.00  
##  Max.   :342.000   Max.   :103.00  
##                    NA's   :38

La lista limpia contiene la información de 2943 multimillonarios:

dim(forbes)
## [1] 2943   11

3.2 Histograma de la variable Edad

# Histograma con mayor frecuencia de etiquetas en eje X
ggplot(forbes, aes(x = Age)) +
  geom_histogram(binwidth = 5, fill = "#383378", color = "white", alpha = 0.9) +
  labs(
    title = "Distribución de la Edad de los Multimillonarios",
    subtitle = "Agrupación por intervalos de 5 años",
    x = "Edad (años)",
    y = "Número de multimillonarios"
  ) +
  scale_x_continuous(breaks = seq(20, 100, by = 10)) +
  theme_minimal(base_family = "sans") +
  theme(
    plot.title = element_text(size = 16, face = "bold", color = "#222222"),
    plot.subtitle = element_text(size = 12, color = "#555555"),
    axis.title = element_text(size = 12),
    axis.text = element_text(size = 10),
    panel.grid.major.y = element_line(color = "grey90"),
    panel.grid.minor = element_blank()
  )

3.3 Histograma del 97% menos rico

# Calcular el percentil 97 del patrimonio neto
p97 <- quantile(forbes$NetWorth, 0.97, na.rm = TRUE)

# Filtrar el 97% inferior
forbes_97 <- forbes %>% filter(NetWorth <= p97)

# Histograma para el 97% menos rico
ggplot(forbes_97, aes(x = NetWorth)) +
  geom_histogram(binwidth = 0.5, fill = "#383378", color = "white", alpha = 0.9) +
  labs(
    title = "Distribución del Patrimonio Neto - 97% menos rico",
    subtitle = "Agrupación por intervalos de $0.5B hasta el percentil 97",
    x = "Net Worth (USD Billions)",
    y = "Número de multimillonarios"
  ) +
  scale_x_continuous(breaks = seq(0, round(p97), by = 1)) + 
  scale_y_continuous(breaks = seq(0, 750, by = 150)) +
  theme_minimal(base_family = "sans") +
  theme(
    plot.title = element_text(size = 16, face = "bold", color = "#222222"),
    plot.subtitle = element_text(size = 12, color = "#555555"),
    axis.title = element_text(size = 12),
    axis.text = element_text(size = 10),
    panel.grid.major.y = element_line(color = "grey90"),
    panel.grid.minor = element_blank()
  )

3.4 Histograma del 3% más rico

# Filtrar el 3% superior
forbes_3 <- forbes %>% filter(NetWorth > p97)

# Histograma para el 3% más rico
ggplot(forbes_3, aes(x = NetWorth)) +
  geom_histogram(binwidth = 10, fill = "#383378", color = "white", alpha = 0.9) +
  labs(
    title = "Distribución del Patrimonio Neto - 3% más rico",
    subtitle = "Intervalos de $10B a partir del percentil 97",
    x = "Net Worth (USD Billions)",
    y = "Número de multimillonarios"
  ) + scale_y_continuous(breaks = seq(0, 30, by = 5)) +
  scale_x_continuous(breaks = seq(floor(min(forbes_3$NetWorth)),
  ceiling(max(forbes_3$NetWorth)), by = 20)) +
  theme_minimal(base_family = "sans") +
  theme(
    plot.title = element_text(size = 16, face = "bold", color = "#222222"),
    plot.subtitle = element_text(size = 12, color = "#555555"),
    axis.title = element_text(size = 12),
    axis.text = element_text(size = 10),
    panel.grid.major.y = element_line(color = "grey90"),
    panel.grid.minor = element_blank()
  )

3.5 Distribución de multimillonarios por país

3.5.1 Top 10 países con más multimillonarios

# Top 10 países con más multimillonarios
top_paises <- forbes %>%
  count(Country, sort = TRUE) %>%
  top_n(10, n)



# Gráfico de barras horizontal
ggplot(top_paises, aes(x = reorder(Country, n), y = n)) +
  geom_bar(stat = "identity", fill = "#383378", alpha = 0.9) +
  labs(
    title = "Top 10 países con más multimillonarios",
    subtitle = "*Hong Kong se considera como país independiente de China",
    x = "País",
    y = "Número de multimillonarios"
  ) +
  coord_flip() +
  scale_y_continuous(breaks = seq(0, max(top_paises$n), by = 75)) +
  theme_minimal(base_family = "sans") +
  theme(
    plot.title = element_text(size = 16, face = "bold", color = "#222222"),
    plot.subtitle = element_text(size = 12, color = "#555555"),
    axis.title = element_text(size = 12),
    axis.text = element_text(size = 10),
    panel.grid.major.x = element_line(color = "grey90"),
    panel.grid.minor = element_blank()
  )

3.5.2 ¿Dónde viven los multimillonarios?

# Corrección de nombres para emparejar con el mapa
forbes_mapa <- forbes %>%
  mutate(Country = recode(Country,
                          "United States" = "United States of America",
                        )) %>%
  count(Country, name = "n_millonarios")

# Cargar geometría mundial
world <- ne_countries(scale = "medium", returnclass = "sf")

# Unir bases
mapa_forbes <- left_join(world, forbes_mapa, by = c("name" = "Country"))

# Crear mapa
ggplot(mapa_forbes) +
  geom_sf(aes(fill = n_millonarios), color = "gray85", size = 0.1) +
  scale_fill_gradient(
    name = "Número de multimillonarios",
    low = "#e0e7ff", high = "#312e81", na.value = "white"
  ) +
  labs(
    title = "¿Dónde viven los multimillonarios?",
    subtitle = "Distribución según la lista Forbes 2025",
    caption = "Fuente: Elaboración propia con datos de Forbes 2025"
  ) +
  coord_sf(
    xlim = c(-160, 180),  
    ylim = c(-55, 85),      
    expand = FALSE
  ) +
  theme_minimal(base_family = "sans") +
  theme(
    plot.title = element_text(size = 18, face = "bold", color = "#1F1F1F"),
    plot.subtitle = element_text(size = 13, face = "plain", color = "#555555"),
    plot.caption = element_text(size = 10, color = "gray50", margin = margin(t = 10)),
    legend.title = element_text(size = 12, face = "bold"),
    legend.text = element_text(size = 10),
    axis.text = element_blank(),
    axis.title = element_blank(),
    panel.grid = element_blank(),
    plot.margin = margin(0, 0, 0, 0)
  )

3.5.3 ¿Dónde viven los multimillonarios en América?

# Filtrar países de América
mapa_america <- mapa_forbes %>%
  filter(region_un == "Americas")

# América: Ajuste de límites geográficos
ggplot(mapa_america) +
  geom_sf(aes(fill = n_millonarios), color = "gray85", size = 0.1) +
  scale_fill_gradient(name = "Número de multimillonarios",
                      low = "#e0e7ff", high = "#312e81", na.value = "white") +
  labs(
    title = "¿Dónde viven los multimillonarios en América?",
    subtitle = "Distribución según la lista Forbes 2025"
  ) +
  coord_sf(xlim = c(-170, -30), ylim = c(-60, 80), expand = FALSE) +
  theme_minimal(base_family = "sans") +
  theme(
    plot.title = element_text(size = 16, face = "bold"),
    plot.subtitle = element_text(size = 12, color = "#555555"),
    axis.text = element_blank(),
    axis.title = element_blank(),
    panel.grid = element_blank()
  )

3.5.4 ¿Dónde viven los multimillonarios en Europa?

# Filtrar países de Europa
mapa_europa <- mapa_forbes %>%
  filter(region_un == "Europe")

# Europa: Ajuste de límites geográficos
ggplot(mapa_europa) +
  geom_sf(aes(fill = n_millonarios), color = "gray85", size = 0.1) +
  scale_fill_gradient(name = "Número de multimillonarios",
                      low = "#e0e7ff", high = "#312e81", na.value = "white") +
  labs(
    title = "¿Dónde viven los multimillonarios en Europa?",
    subtitle = "Distribución según la lista Forbes 2025"
  ) +
  coord_sf(xlim = c(-30, 70), ylim = c(30, 75), expand = FALSE) +
  theme_minimal(base_family = "sans") +
  theme(
    plot.title = element_text(size = 16, face = "bold"),
    plot.subtitle = element_text(size = 12, color = "#555555"),
    axis.text = element_blank(),
    axis.title = element_blank(),
    panel.grid = element_blank()
  )

3.5.5 ¿Dónde viven los multimillonarios en Asia?

# Filtrar países de Asia
mapa_asia <- mapa_forbes %>%
  filter(region_un == "Asia")

# Asia: Ajuste de límites geográficos
ggplot(mapa_asia) +
  geom_sf(aes(fill = n_millonarios), color = "gray85", size = 0.1) +
  scale_fill_gradient(name = "Número de multimillonarios",
                      low = "#e0e7ff", high = "#312e81", na.value = "white") +
  labs(
    title = "¿Dónde viven los multimillonarios en Asia?",
    subtitle = "Distribución según la lista Forbes 2025"
  ) +
  theme_minimal(base_family = "sans") +
  theme(
    plot.title = element_text(size = 16, face = "bold"),
    plot.subtitle = element_text(size = 12, color = "#555555"),
    axis.text = element_blank(),
    axis.title = element_blank(),
    panel.grid = element_blank()
  )

4. Análisis por Industria e Ingresos

4.1 Industrias con mayor número de multimillonarios

# Agrupar por industria
industria_total <- forbes %>%
  count(Industry, sort = TRUE)

# Gráfico
ggplot(industria_total, aes(x = reorder(Industry, n), y = n)) +
  geom_bar(stat = "identity", fill = "#383378", alpha = 0.9) +
  labs(
    title = "Número de multimillonarios por industria",
    subtitle = "Distribución total según la lista Forbes 2025",
    x = "Industria",
    y = "Número de multimillonarios"
  ) +
  coord_flip() +
  theme_minimal(base_family = "sans") +
  theme(
    plot.title = element_text(size = 15, face = "bold"),
    plot.subtitle = element_text(size = 11, color = "#555555"),
    axis.title = element_text(size = 11),
    axis.text = element_text(size = 10)
  )

# Calcular proporciones
industria_prop <- industria_total %>%
  mutate(porcentaje = round(100 * n / sum(n), 1))

# Gráfico con etiquetas de porcentaje
ggplot(industria_prop, aes(x = reorder(Industry, porcentaje), y = porcentaje)) +
  geom_bar(stat = "identity", fill = "#383378", alpha = 0.9) +
  geom_text(aes(label = paste0(porcentaje, "%")), hjust = -0.1, size = 3.2, color = "black") +
  labs(
    title = "Proporción de multimillonarios por industria",
    subtitle = "Distribución total según la lista Forbes 2025",
    x = "Industria",
    y = "Porcentaje"
  ) +
  coord_flip() +
  scale_y_continuous(limits = c(0, 20), breaks = seq(0, 18, by = 2.5)) +  
  theme_minimal(base_family = "sans") +
  theme(
    plot.title = element_text(size = 15, face = "bold"),
    plot.subtitle = element_text(size = 11, color = "#555555"),
    axis.title = element_text(size = 11),
    axis.text = element_text(size = 10)
  )

4.2 Industrias con mayor patrimonio agregado

# Calcular patrimonio total por industria
industria_riqueza <- forbes %>%
  group_by(Industry) %>%
  summarise(PatrimonioTotal = sum(NetWorth, na.rm = TRUE)) %>%
  arrange(desc(PatrimonioTotal))

# Gráfico
ggplot(industria_riqueza, aes(x = reorder(Industry, PatrimonioTotal), y = PatrimonioTotal)) +
  geom_bar(stat = "identity", fill = "#383378", alpha = 0.9) +
  labs(
    title = "Patrimonio neto agregado por industria",
    subtitle = "Distribución total según la lista Forbes 2025",
    x = "Industria",
    y = "Patrimonio total"
  ) +
  coord_flip() +
  scale_y_continuous(breaks = seq(0, max(industria_riqueza$PatrimonioTotal), by = 500)) +
  theme_minimal(base_family = "sans") +
  theme(
    plot.title = element_text(size = 15, face = "bold"),
    plot.subtitle = element_text(size = 11, color = "#555555"),
    axis.title = element_text(size = 11),
    axis.text = element_text(size = 10)
  )

# Calcular proporción del total
industria_riqueza_prop <- industria_riqueza %>%
  mutate(Porcentaje = round(100 * PatrimonioTotal / sum(PatrimonioTotal), 1))

# Gráfico
ggplot(industria_riqueza_prop, aes(x = reorder(Industry, Porcentaje), y = Porcentaje)) +
  geom_bar(stat = "identity", fill = "#383378", alpha = 0.9) +
  geom_text(aes(label = paste0(Porcentaje, "%")), hjust = -0.1, size = 3.2, color = "black") +
  labs(
    title = "Proporción del patrimonio total por industria",
    subtitle = "Distribución total según la lista Forbes 2025",
    x = "Industria",
    y = "Porcentaje") +coord_flip() +
  scale_y_continuous(limits = c(0, 25), breaks = seq(0, 25, by = 5)) +  # Ajusta si hay más dispersión
  theme_minimal(base_family = "sans") + theme( plot.title = element_text(size = 15, face = "bold"),
    plot.subtitle = element_text(size = 11, color = "#555555"),axis.title = element_text(size = 11),
    axis.text = element_text(size = 10)
  )

4.3 Cantidad de multimillonarios vs Patrimonio agregado

abreviaciones <- c(
  "Technology" = "Tech",
  "Finance & Investments" = "Fin",
  "Fashion & Retail" = "F&R",
  "Manufacturing" = "Mfg",
  "Food & Beverage" = "F&B",
  "Diversified" = "Div",
  "Healthcare" = "Hlth",
  "Real Estate" = "RE",
  "Automotive" = "Auto",
  "Energy" = "En",
  "Media & Entertainment" = "M&E",
  "Metals & Mining" = "M&M",
  "Engineering" = "Eng",
  "Logistics" = "Log",
  "Construction & Engineering" = "C&E",
  "Telecom" = "Tel",
  "Service" = "Svc",
  "Gambling & Casinos" = "G&C"
)

# Número de personas por industria
industria_n <- forbes %>%
  count(Industry, name = "NumMillonarios")

# Patrimonio total por industria
industria_riqueza <- forbes %>%
  group_by(Industry) %>%
  summarise(PatrimonioTotal = sum(NetWorth, na.rm = TRUE))

# Combinar ambas
industria_comparacion <- left_join(industria_n, industria_riqueza, by = "Industry")

# Alterar nombre de la industrias por abreviaturas
industria_comparacion <- industria_comparacion %>%
  mutate(IndustriaAbrev = abreviaciones[Industry])

# Crear leyenda textual
leyenda_abrevs <- paste0(names(abreviaciones), " = ", abreviaciones, collapse = " | ")

# Aplicar abreviaciones
industria_comparacion <- industria_comparacion %>%
  mutate(IndustriaAbrev = abreviaciones[Industry])

# Caption
caption = paste(
  "Abreviaturas:",
  "Tech = Technology | Fin = Finance & Investments
  | F&R = Fashion & Retail | Mfg = Manufacturing | F&B = Food & Beverage",
  "| Div = Diversified,
  Hlth = Healthcare | RE = Real Estate | 
  Auto = Automotive | En = Energy | M&E = Media & Entertainment | M&M = Metals & Mining |",
  "Eng = Engineering | Log = Logistics | C&E = Construction & Engineering 
  | Tel = Telecom | Svc = Service | G&C = Gambling & Casinos",
  sep = "\n"
)


# Gráfico final
ggplot(industria_comparacion, aes(x = NumMillonarios, y = PatrimonioTotal)) +
  geom_point(aes(size = PatrimonioTotal), color = "#383378", alpha = 0.8) +
  geom_label_repel(
    aes(label = IndustriaAbrev),
    size = 4, color = "black", box.padding = 0.4,
    segment.color = "gray60", max.overlaps = 20, label.size = 0.2
  ) +
  scale_size(range = c(3, 10), guide = "none") +
  scale_y_continuous(limits = c(0, 3500), breaks = seq(0, 3500, 500)) +
  labs(
    title = "Scatter plot: ¿Cantidad o concentración? ",
    subtitle = "Relación entre número de multimillonarios y riqueza total",
    x = "Número de multimillonarios",
    y = "Patrimonio total (USD Billions)",
    caption = paste(
      "Abreviaturas:",
      "Tech = Technology | Fin = Finance & Investments | F&R = Fashion & Retail | Mfg = Manufacturing | F&B = Food & Beverage | ",
      " Div = Diversified | Hlth = Healthcare | RE = Real Estate | Auto = Automotive | En = Energy | M&E = Media & Entertainment |", 
      " M&M = Metals & Mining | Log = Logistics | C&E = Construction & Engineering | Tel = Telecom | Svc = Service |", 
      "| G&C = Gambling & Casinos |",
      sep = "\n"
    )
  ) +
  theme_minimal(base_family = "sans") +
  theme(
    plot.title = element_text(size = 15, face = "bold"),
    plot.subtitle = element_text(size = 11, color = "#555555"),
    plot.caption = element_text(size = 9, color = "gray50", margin = margin(t = 10)),
    axis.title = element_text(size = 11),
    axis.text = element_text(size = 10)
  )

4.4 Distribución de edad por industria

# Filtrar datos válidos
forbes_filtrado <- forbes %>% filter(!is.na(Age))

# Ordenar industrias por mediana de edad (descendente)
orden_industrias <- forbes_filtrado %>%
  group_by(Industry) %>%
  summarise(MedianaEdad = median(Age, na.rm = TRUE)) %>%
  arrange(desc(MedianaEdad)) %>%
  pull(Industry)

# Gráfico
ggplot(forbes_filtrado, aes(x = factor(Industry, levels = orden_industrias), y = Age)) +
  geom_boxplot(
    fill = "#383378", color = "white", outlier.shape = 21,
    outlier.fill = "#e63946", outlier.color = "black", outlier.size = 2, alpha = 0.85
  ) +
  scale_y_continuous(breaks = seq(0, 100, by = 15)) +  # Eje Y de 15 en 15
  labs(
    title = "Distribución de la edad por industria",
    subtitle = "Ordenado de menor a mayor mediana",
    x = "Industria",
    y = "Edad (años)"
  ) +
  coord_flip() +
  theme_minimal(base_family = "sans") +
  theme(
    plot.title = element_text(size = 16, face = "bold", hjust = 0.5),
    plot.subtitle = element_text(size = 11, color = "#555555", hjust = 0.5),
    axis.title = element_text(size = 11),
    axis.text.y = element_text(size = 9),
    axis.text.x = element_text(size = 10),
    panel.grid.major.x = element_line(color = "gray80", size = 0.4),
    panel.grid.major.y = element_blank(),
    panel.grid.minor = element_blank() 
  )

5. Comparativa: Colombia vs Pares latinoamericanos

5.1 Número de multimillonarios por país

# Filtrar países de interés
latam <- c("Colombia", "Mexico", "Brazil", "Argentina", "Chile")

# Número de multimillonarios
n_millonarios_latam <- forbes %>%
  filter(Country %in% latam) %>%
  count(Country, name = "NumMillonarios")

# Vector de colores por país
colores_latam <- c(
  "Colombia"  = "#ffff00",
  "Mexico"    = "#178b2e",  
  "Brazil"    = "#0106b4",  
  "Argentina" = "#85fff9",  
  "Chile"     = "#ff4b4b"   
)

# Gráfica
ggplot(n_millonarios_latam, aes(x = reorder(Country, -NumMillonarios), 
                                y = NumMillonarios, fill = Country)) +
  geom_bar(stat = "identity", width = 0.65, color = "white", alpha = 0.9) +
  geom_text(
    aes(label = NumMillonarios),
    vjust = -0.6, size = 4, color = "#222222"
  ) +
  scale_fill_manual(values = colores_latam) +
  scale_y_continuous(limits = c(0, 55), breaks = seq(0, 55, by = 5)) +
  labs(
    title = "Número de multimillonarios por país",
    subtitle = "Comparativa regional: Colombia vs pares latinoamericanos",
    x = NULL,
    y = "Cantidad de multimillonarios"
  ) +
  theme_minimal(base_family = "sans") +
  theme(
    plot.title = element_text(size = 16, face = "bold", hjust = 0.5),
    plot.subtitle = element_text(size = 12, color = "#555555", hjust = 0.5),
    axis.title.y = element_text(size = 11),
    axis.title.x = element_blank(),
    axis.text = element_text(size = 10),
    panel.grid.major.y = element_line(color = "gray90"),
    panel.grid.minor = element_blank(),
    legend.position = "none",
    plot.margin = margin(10, 20, 10, 20)
  )

5.2 Patrimonio neto por país

# Crear Df "riqueza_latam"
riqueza_latam <- forbes %>%
  filter(Country %in% latam) %>%
  group_by(Country) %>%
  summarise(PatrimonioTotal = sum(NetWorth, na.rm = TRUE)) %>%
  arrange(desc(PatrimonioTotal))

# Gráfica
ggplot(riqueza_latam, aes(x = reorder(Country, -PatrimonioTotal), y = PatrimonioTotal, fill = Country)) +
  geom_bar(stat = "identity", width = 0.65, color = "white", alpha = 0.9) +
  geom_text(
    aes(label = round(PatrimonioTotal, 1)),
    vjust = -0.6, size = 4, color = "#222222"
  ) +
  scale_fill_manual(values = colores_latam) +
  scale_y_continuous(limits = c(0, max(riqueza_latam$PatrimonioTotal) + 30), breaks = seq(0, 300, by = 50)) +
  labs(
    title = "Patrimonio total de multimillonarios por país",
    subtitle = "Comparativa regional: Colombia vs pares latinoamericanos",
    x = NULL,
    y = "Patrimonio total (USD Billions)"
  ) +
  theme_minimal(base_family = "sans") +
  theme(
    plot.title = element_text(size = 16, face = "bold", hjust = 0.5),
    plot.subtitle = element_text(size = 12, color = "#555555", hjust = 0.5),
    axis.title.y = element_text(size = 11),
    axis.title.x = element_blank(),
    axis.text = element_text(size = 10),
    panel.grid.major.y = element_line(color = "gray90"),
    panel.grid.minor = element_blank(),
    legend.position = "none",
    plot.margin = margin(10, 20, 10, 20)
  )

5.3 Principales industrias de Latam

# Industrias que conforman la riqueza en Latam
industria_total_latam <- forbes %>%
  filter(Country %in% latam) %>%
  group_by(Industry) %>%
  summarise(PatrimonioTotal = sum(NetWorth, na.rm = TRUE)) %>%
  arrange(desc(PatrimonioTotal)) %>%
  mutate(
    Etiqueta = paste0(round(PatrimonioTotal, 1), "B")  # Solo el patrimonio
  )

# Gráfico de barras
ggplot(industria_total_latam, aes(x = reorder(Industry, PatrimonioTotal), y = PatrimonioTotal)) +
  geom_bar(stat = "identity", fill = "#383378", width = 0.65, color = "white", alpha = 0.95) +
  geom_text(aes(label = Etiqueta), hjust = -0.2, size = 3.2, color = "#222222") +
  scale_y_continuous(limits = c(0, max(industria_total_latam$PatrimonioTotal) + 30)) +
  labs(
    title = "Distribución de patrimonio por industria",
    subtitle = "Patrimonio total (USD Billions) sumado por sector",
    x = "Industria",
    y = "Patrimonio total (USD Billions)"
  ) +
  coord_flip() +
  theme_minimal(base_family = "sans") +
  theme(
    plot.title = element_text(size = 15, face = "bold", hjust = 0.5),
    plot.subtitle = element_text(size = 11, color = "#555555", hjust = 0.5),
    axis.title = element_text(size = 11),
    axis.text = element_text(size = 10)
  )

# Proporción de patrimonio 
industria_total_latam <- forbes %>%
  filter(Country %in% latam) %>%
  group_by(Industry) %>%
  summarise(PatrimonioTotal = sum(NetWorth, na.rm = TRUE)) %>%
  mutate(
    Proporcion = round(100 * PatrimonioTotal / sum(PatrimonioTotal), 1)  
  ) %>%
  arrange(desc(Proporcion))

# Gráfico de barras solo porcentaje
ggplot(industria_total_latam, aes(x = reorder(Industry, Proporcion), y = Proporcion)) +
  geom_bar(stat = "identity", fill = "#383378", width = 0.65, color = "white", alpha = 0.95) +
  geom_text(aes(label = paste0(Proporcion, "%")), hjust = -0.2, size = 3.2, color = "#222222") +
  scale_y_continuous(
    limits = c(0, max(industria_total_latam$Proporcion) + 5),
    breaks = seq(0, 100, by = 5)  # Líneas cada 5%
  ) +
  labs(
    title = "Distribución de patrimonio por industria",
    subtitle = "Proporción sobre el patrimonio total",
    x = "Industria",
    y = "Porcentaje del patrimonio (%)"
  ) +
  coord_flip() +
  theme_minimal(base_family = "sans") +
  theme(
    plot.title = element_text(size = 15, face = "bold", hjust = 0.5),
    plot.subtitle = element_text(size = 11, color = "#555555", hjust = 0.5),
    axis.title = element_text(size = 11),
    axis.text = element_text(size = 10),
    panel.grid.major.x = element_line(color = "gray85", size = 0.4),  # Grilla suave horizontal
    panel.grid.minor = element_blank()
  )

6. Comparativa regional: EE.UU. vs Europa vs China

# Definir países de la Unión Europea y Europa Ampliada
paises_europa <- c(
  "Germany", "France", "Italy", "Spain", "Netherlands", "Poland", "Sweden", "Belgium", "Austria",
  "Denmark", "Finland", "Portugal", "Ireland", "Czech Republic", "Greece", "Hungary", "Slovakia",
  "Bulgaria", "Croatia", "Lithuania", "Slovenia", "Latvia", "Estonia", "Luxembourg", "Malta", 
  "Cyprus", "Romania", "United Kingdom", "Switzerland", "Norway", "Iceland", "Serbia", "Ukraine",
  "Bosnia and Herzegovina", "Albania", "North Macedonia", "Moldova", "Kosovo", "Monaco",
  "Liechtenstein", "Andorra", "San Marino"
)

# Crear la nueva variable "Bloque"
forbes <- forbes %>%
  mutate(Bloque = case_when(
    Country == "United States" ~ "EE.UU.",
    Country == "China" ~ "China",
    Country %in% paises_europa ~ "Europa",
    TRUE ~ NA_character_
  ))

6.1 Número de multimillonarios por bloque

# Filtrar multimillonarios de los bloques de interés
forbes_bloques <- forbes %>%
  filter(!is.na(Bloque))

# Contar número de multimillonarios por bloque
n_millonarios_bloque <- forbes_bloques %>%
  count(Bloque, name = "NumMillonarios") %>%
  arrange(desc(NumMillonarios))

# Definir colores para los bloques
colores_bloques <- c(
  "EE.UU." = "#1f77b4",  
  "China" = "#d62728",   
  "Europa" = "#2ca02c" 
)

# Reordenar el factor 'Bloque' para controlar el orden en la leyenda y en el gráfico
n_millonarios_bloque <- n_millonarios_bloque %>%
  mutate(Bloque = factor(Bloque, levels = c("EE.UU.", "Europa", "China")))

# Gráfico 
ggplot(n_millonarios_bloque, aes(x = reorder(Bloque, -NumMillonarios), y = NumMillonarios, fill = Bloque)) +
  geom_bar(stat = "identity", width = 0.45, color = "white", alpha = 0.9) +
  geom_text(
    aes(label = NumMillonarios),
    vjust = -0.7, size = 4, color = "black", fontface = "plain"  
  ) +
  scale_fill_manual(values = colores_bloques, name = "Bloque económico: ") +
  scale_y_continuous(
    limits = c(0, max(n_millonarios_bloque$NumMillonarios) + 50),
    breaks = seq(0, max(n_millonarios_bloque$NumMillonarios) + 50, by = 200),
    expand = expansion(mult = c(0, 0.08))
  ) +
  labs(
    title = "Número de multimillonarios por bloque económico",
    subtitle = "Bloques: EE.UU., Europa y China",
    x = NULL,
    y = "Cantidad de multimillonarios"
  ) +
  theme_minimal(base_family = "sans") +
  theme(
    plot.background = element_rect(fill = "#f7f7f7", color = NA),  
    panel.background = element_rect(fill = "#f7f7f7", color = NA),
    plot.title = element_text(size = 17, face = "bold", color = "#222222", hjust = 0.5),
    plot.subtitle = element_text(size = 12, color = "#666666", hjust = 0.5),
    axis.title.y = element_text(size = 12),
    axis.text.x = element_text(size = 11),
    axis.text.y = element_text(size = 11),
    panel.grid.major.y = element_line(color = "gray85", size = 0.4),
    panel.grid.minor = element_blank(),
    plot.margin = margin(15, 20, 12, 20),
    legend.position = "top",        # 
    legend.title = element_text(size = 11),
    legend.text = element_text(size = 10)
  )

6.2 Patrimonio total por bloque

# Sumar patrimonio total por bloque
patrimonio_bloque <- forbes_bloques %>%
  group_by(Bloque) %>%
  summarise(PatrimonioTotal = sum(NetWorth, na.rm = TRUE)) %>%
  arrange(desc(PatrimonioTotal))

# Reordenar el factor 'Bloque' para controlar el orden en la leyenda y en el gráfico
patrimonio_bloque <- patrimonio_bloque %>%
  mutate(Bloque = factor(Bloque, levels = c("EE.UU.", "Europa", "China")))

# Gráfico
ggplot(patrimonio_bloque, aes(x = Bloque, y = PatrimonioTotal, fill = Bloque)) +
  geom_bar(stat = "identity", width = 0.45, color = "white", alpha = 0.95) +
  geom_text(
    aes(label = paste0(round(PatrimonioTotal, 1), "B")),
    vjust = -0.7, size = 4, color = "black"
  ) + scale_fill_manual(
    values = colores_bloques,
    name = "Bloque económico"
  ) + scale_y_continuous(
    limits = c(0, max(patrimonio_bloque$PatrimonioTotal) * 1.15),
    expand = expansion(mult = c(0, 0.08))
  ) + labs(
    title = "Patrimonio total por bloque económico",
    subtitle = "Suma de los patrimonios netos (USD Billions)",
    x = NULL,
    y = "Patrimonio total (USD Billions)"
  ) +
  theme_minimal(base_family = "sans") +
  theme(
    plot.background = element_rect(fill = "#f7f7f7", color = NA),
    panel.background = element_rect(fill = "#f7f7f7", color = NA),
    plot.title = element_text(size = 17, face = "bold", hjust = 0.5),
    plot.subtitle = element_text(size = 12, color = "#666666", hjust = 0.5),
    axis.title.y = element_text(size = 12),
    axis.text = element_text(size = 10),
    panel.grid.major.y = element_line(color = "gray85", size = 0.4),
    panel.grid.minor = element_blank(),
    plot.margin = margin(15, 20, 12, 20),
    legend.position = "top",
    legend.title = element_text(size = 11),
    legend.text = element_text(size = 10)
  )

6.3 Distribución industrial: Top 6 industrias por patrimonio en cada bloque

# Para EE.UU.
top6_usa <- forbes_bloques %>%
  filter(Bloque == "EE.UU.") %>%
  group_by(Industry) %>%
  summarise(PatrimonioTotal = sum(NetWorth, na.rm = TRUE)) %>%
  slice_max(order_by = PatrimonioTotal, n = 6) %>%
  arrange(PatrimonioTotal)

# Para China
top6_china <- forbes_bloques %>%
  filter(Bloque == "China") %>%
  group_by(Industry) %>%
  summarise(PatrimonioTotal = sum(NetWorth, na.rm = TRUE)) %>%
  slice_max(order_by = PatrimonioTotal, n = 6) %>%
  arrange(PatrimonioTotal)

# Para Europa
top6_ue <- forbes_bloques %>%
  filter(Bloque == "Europa") %>%
  group_by(Industry) %>%
  summarise(PatrimonioTotal = sum(NetWorth, na.rm = TRUE)) %>%
  slice_max(order_by = PatrimonioTotal, n = 6) %>%
  arrange(PatrimonioTotal)

6.3.1 Industrias de mayor patrimonio en EE.UU.

# Gráfico EE.UU.
ggplot(top6_usa, aes(x = reorder(Industry, PatrimonioTotal), y = PatrimonioTotal)) +
  geom_bar(stat = "identity", fill = "#1f77b4", width = 0.6, color = "white", alpha = 0.9) +
  geom_text(aes(label = paste0(round(PatrimonioTotal, 1), "B")),
            hjust = -0.2, size = 3.3, color = "#222222") +
  labs(
    title = "Top 6 Industrias - EE.UU.",
    subtitle = "Patrimonio total (USD Billions)",
    x = NULL,
    y = "Patrimonio total"
  ) +
  scale_y_continuous(limits = c(0, max(top6_usa$PatrimonioTotal) * 1.2)) +
  coord_flip() +
  theme_minimal(base_family = "sans") +
  theme(
    plot.title = element_text(size = 16, face = "bold", hjust = 0.5),
    plot.subtitle = element_text(size = 12, color = "#555555", hjust = 0.5),
    axis.title.y = element_blank(),
    axis.text = element_text(size = 10)
  )

6.3.2 Industrias de mayor patrimonio en China

# Gráfico China
ggplot(top6_china, aes(x = reorder(Industry, PatrimonioTotal), y = PatrimonioTotal)) +
  geom_bar(stat = "identity", fill = "#d62728", width = 0.6, color = "white", alpha = 0.9) +
  geom_text(aes(label = paste0(round(PatrimonioTotal, 1), "B")),
            hjust = -0.2, size = 3.3, color = "#222222") +
  labs(
    title = "Top 6 Industrias - China",
    subtitle = "Patrimonio total (USD Billions)",
    x = NULL,
    y = "Patrimonio total"
  ) +
  scale_y_continuous(limits = c(0, max(top6_china$PatrimonioTotal) * 1.2)) +
  coord_flip() +
  theme_minimal(base_family = "sans") +
  theme(
    plot.title = element_text(size = 16, face = "bold", hjust = 0.5),
    plot.subtitle = element_text(size = 12, color = "#555555", hjust = 0.5),
    axis.title.y = element_blank(),
    axis.text = element_text(size = 10)
  )

6.3.3 Industrias de mayor patrimonio en Europa

# Gráfico para Europa
ggplot(top6_ue, aes(x = reorder(Industry, PatrimonioTotal), y = PatrimonioTotal)) +
  geom_bar(stat = "identity", fill = "#2ca02c", width = 0.6, color = "white", alpha = 0.9) +
  geom_text(aes(label = paste0(round(PatrimonioTotal, 1), "B")), hjust = -0.2,
            size = 3.3, color = "#222222") +
  labs(
    title = "Top 6 Industrias - Europa",
    subtitle = "Patrimonio total (USD Billions)",
    x = NULL,
    y = "Patrimonio total"
  ) +
  scale_y_continuous(limits = c(0, max(top6_ue$PatrimonioTotal) * 1.2)) +
  coord_flip() +
  theme_minimal(base_family = "sans") +
  theme(
    plot.title = element_text(size = 16, face = "bold", hjust = 0.5),
    plot.subtitle = element_text(size = 12, color = "#555555", hjust = 0.5),
    axis.title.y = element_blank(),
    axis.text = element_text(size = 10)
  )

6.4 Comparativa entre bloques para las 6 industrias principales

# Establecer industrias clave (originales)
industrias_clave <- c(
  "Technology", "Finance & Investments",
  "Fashion & Retail", "Food & Beverage", "Manufacturing", "Automotive"
)

# Diccionario de abreviaciones
abreviaturas_industrias <- c(
  "Technology" = "Tech",
  "Finance & Investments" = "Fin",
  "Fashion & Retail" = "F&R",
  "Food & Beverage" = "F&B",
  "Manufacturing" = "Mfg",
  "Automotive" = "Auto"
)

# Filtrar, agrupar, calcular patrimonio por bloque e industria
patrimonio_bloques_industrias <- forbes_bloques %>%
  filter(Industry %in% industrias_clave) %>%
  group_by(Bloque, Industry) %>%
  summarise(PatrimonioTotal = sum(NetWorth, na.rm = TRUE), .groups = "drop") %>%
  mutate(
    Industry = abreviaturas_industrias[as.character(Industry)],  # aplicar reemplazo
    Bloque = factor(Bloque, levels = c("EE.UU.", "China", "Europa")),
    Industry = factor(Industry, levels = abreviaturas_industrias)  # orden
  )

# Orden de barras
patrimonio_bloques_industrias <- patrimonio_bloques_industrias %>%
  mutate(Bloque = factor(Bloque, levels = c("EE.UU.", "Europa", "China")))

# Gráfico
ggplot(patrimonio_bloques_industrias, aes(x = Industry, y = PatrimonioTotal, fill = Bloque)) +
  geom_bar(stat = "identity", position = position_dodge(width = 0.7),
           width = 0.6, color = "white", alpha = 0.95) +
  scale_fill_manual(
    values = colores_bloques,
    name = "Bloque económico",
    breaks = c("EE.UU.", "Europa", "China")
  ) + scale_y_continuous(
    breaks = seq(0, max(patrimonio_bloques_industrias$PatrimonioTotal) + 250, by = 250),
    expand = expansion(mult = c(0, 0.1))
  ) +labs(
    title = "Distribución del patrimonio por industria",
    subtitle = "Tecnología, Finanzas, Moda, Alimentos, Manufactura y Automóviles (USD Billions)",
    x = "Industria",
    y = "Patrimonio total (USD Billions)"
  ) +
  theme_minimal(base_family = "sans") +
  theme(
    plot.background = element_rect(fill = "#f7f7f7", color = NA),
    panel.background = element_rect(fill = "#f7f7f7", color = NA),
    plot.title = element_text(size = 17, face = "bold", hjust = 0.5),
    plot.subtitle = element_text(size = 12, color = "#555555", hjust = 0.5),
    axis.title = element_text(size = 12),
    axis.text = element_text(size = 10),
    panel.grid.major.y = element_line(color = "gray85", size = 0.4),
    panel.grid.minor = element_blank(),
    legend.position = "top",
    legend.title = element_text(size = 11),
    legend.text = element_text(size = 10),
    plot.margin = margin(15, 20, 12, 20)
  )

# Crear tabla con proporciones relativas por industria
proporcion_por_bloque <- patrimonio_bloques_industrias %>%
  group_by(Industry) %>%
  mutate(Proporcion = round(100 * PatrimonioTotal / sum(PatrimonioTotal), 1)) %>%
  ungroup()

# Invertir niveles para que EE.UU. esté abajo en el apilado
proporcion_por_bloque <- proporcion_por_bloque %>%
  mutate(Bloque = factor(Bloque, levels = c("China", "Europa", "EE.UU.")))

# Gráfico
ggplot(proporcion_por_bloque, aes(x = Industry, y = Proporcion, fill = Bloque)) +
  geom_bar(stat = "identity", width = 0.6, color = "white", alpha = 0.95) +
  scale_fill_manual(
    values = colores_bloques,
    name = "Bloque económico",
    breaks = c("EE.UU.", "Europa", "China")
  ) +
  scale_y_continuous(
    limits = c(0, 100),
    breaks = seq(0, 100, by = 10),
    expand = expansion(mult = c(0, 0))
  ) +
  labs(
    title = "Distribución relativa del patrimonio por industria",
   subtitle = "Tecnología - Finanzas - Moda - Alimentos - Manufactura - Automóviles (%)",
    x = "Industria",
    y = "Participación (%)"
  ) +
  theme_minimal(base_family = "sans") +
  theme(
    plot.background = element_rect(fill = "#f7f7f7", color = NA),
    panel.background = element_rect(fill = "#f7f7f7", color = NA),
    plot.title = element_text(size = 17, face = "bold", hjust = 0.5),
    plot.subtitle = element_text(size = 12, color = "#555555", hjust = 0.5),
    axis.title = element_text(size = 12),
    axis.text = element_text(size = 10),
    panel.grid.major.y = element_line(color = "gray85", size = 0.4),
    panel.grid.minor = element_blank(),
    legend.position = "top",
    legend.title = element_text(size = 11),
    legend.text = element_text(size = 10),
    plot.margin = margin(15, 20, 12, 20)
  )